Mojo function

batched_matmul_kernel_gpu

batched_matmul_kernel_gpu[c_type: DType, a_type: DType, b_type: DType, layout_c: Layout, layout_a: Layout, layout_b: Layout, transpose_b: Bool, config: MatmulConfig[a_type, b_type, c_type, transpose_b], elementwise_lambda_fn: OptionalReg[fn[DType, Int, Int, Int](IndexList[$2], SIMD[$0, $1]) capturing -> None] = OptionalReg[fn[DType, Int, Int, Int](IndexList[$2], SIMD[$0, $1]) capturing -> None]({:i1 0, 1})](c_tensor: LayoutTensor[c_type, layout_c, MutableAnyOrigin], a_tensor: LayoutTensor[a_type, layout_a, MutableAnyOrigin], b_tensor: LayoutTensor[b_type, layout_b, MutableAnyOrigin], m: Int, n: Int, k: Int)